mosmafs v0.1.2


Monthly downloads



Multi-Objective Simultaneous Model and Feature Selection

Performs simultaneous hyperparameter tuning and feature selection through both single-objective and multi-objective optimization as described in Binder, Moosbauer et al. (2019) <arXiv:1912.12912>. Uses the 'ecr'-package as basis but adds mixed integer evolutionary strategies and multi-fidelity functionality as well as operators specific for the problem of feature selection.


MOSMaFS: Multi-Objective Simultaneous Model and Feature Selection

Travis build status Coverage CRAN Status Badge CRAN Downloads

Project Status

We are on CRAN! You can also read our paper on arxiv.


It is best to install the official version from CRAN. If you want to live on the edge, you can also install the github version, using remotes:

remotes::install_github("compstat-lmu/mosmafs", ref = "mosmafs-package")



If mosmafs is useful for your research, please cite our paper:

Binder, Martin., Moosbauer, J. et al. "Model-Agnostic Approaches to Multi-Objective Simultaneous Hyperparameter Tuning and Feature Selection." arXiv preprint arXiv:1912.12912 (2019).


    title={Multi-Objective Hyperparameter Tuning and Feature Selection using Filter Ensembles},
    author={Martin Binder and Julia Moosbauer and Janek Thomas and Bernd Bischl},


MIT License

Functions in mosmafs

Name Description
fitnesses Extract Fitnesses from ECR Log
getStatistics Get Statistics
mosmafsTermEvals Termination Function Creator
cpoSelector CPO that Selects Features
initSelector Initialize Selector
mutBitflipCHW Bitflip (Approximately, in Expectation) Conserving Hamming Weight
listToDf List to data.frame
mutGaussScaled Scaled Gaussian Mutator
makeBaselineObjective Create mlrMBO Objective Function
mutGaussIntScaled Integer Scaled Gaussian Mutator
intifyMutator Turn Continuous-Space Operators into Integer-Space Operators
makeFilterStrategy Create a Filter Strategy Function
makeFilterMat Create a Filter-Matrix
naiveHoldoutDomHV Naive Hypervolume on Holdout Data
slickEcr Modified Interface to ECR
mutDoubleGeom Double Geometric Distribution Mutator
mutUniformResetSHW Uniform Reset Scaled by Hamming Weight
slickEvaluateFitness Compute the Fitness of Individuals
makeObjective Create ecr Objective Function
mutUniformParametric Parametric Uniform Mutation
mutGaussInt Integer Gaussian Mutator
getPopulations Get Populations
recPCrossover General Uniform Crossover
mutPolynomialInt Integer Polynomial Mutator
paretoEdges Get Pareto Front Edges from Fitness Matrix
overallRankMO Rank by Nondominated Front and Crowding Distance or Hypervolume Contribution
recIntIntermediate Integer Intermediate Recombinator
recIntSBX Integer SBX Recombinator
mutRandomChoice Random Choice Mutator
task.add.permuted.cols Add Permuted Noise-Features to Task
mutUniformInt Integer Uniform Mutator
selSimpleUnique Simple Selector without Replacement
task.add.random.cols Add Sampled Noise-Features to Task
unbiasedHoldoutDomHV Unbiased Dominated Hypervolume on Holdout Data
mutUniformMetaReset Parametrised Uniform Reset for Binary Parameters
recGaussian Gaussian Intermediate Recombinator
popAggregate Aggregate Population Results
valuesFromNames Convert Discrete Parameters from Names to Values
mutUniformReset Uniform Reset for Binary Parameters
selTournamentMO Multi-Objective k-Tournament Selector
setMosmafsVectorized Set mosmafs.vectorize
constructEvalSetting Parameter Configuration of Mosmafs
clonetask Replace Data in Task with new Data Create Hypersphere Data
combine.operators Combine ECR-Operators
collectResult Collect Result Information Create Linear Model Data Linear Toy Data
availableAttributes List Attributes that can be Aggregated
create.regr.task Create mlr-Task from Data
No Results!

Vignettes of mosmafs

No Results!

Last month downloads


License MIT + file LICENSE
Encoding UTF-8
ByteCompile yes
VignetteBuilder knitr
RoxygenNote 7.0.2
Collate 'customnsga2.R' 'datagen.R' 'ecrshims.R' 'evalmosmafs.R' 'filtermat.R' 'objective.R' 'utils.R' 'operators.R' 'plotting.R' 'selectorcpo.R' 'terminators.R' 'zzz.R'
NeedsCompilation no
Packaged 2020-04-05 20:51:06 UTC; user
Repository CRAN
Date/Publication 2020-04-05 21:40:03 UTC

Include our badge in your README